DATA ANALYTICS INTERVIEW GUIDE

QnA
Covers: Concepts ▪ SQL ▪ Excel ▪ Python ▪ Power BI ▪ Statistics ▪ Case Studies ▪ HR + Managerial

SECTION 1 — DATA ANALYTICS (30 Questions +

Answers + Examples)
Most commonly & frequently asked in Interviews.

a
llik
1. What is Data Analytics?

Answer: The process of cleaning, transforming and analyzing data to extract

insights.​
va
Example: Identify why revenue dropped last quarter using transaction data.
a
2. Types of Data Analytics?
Pr

Answer: Descriptive, Diagnostic, Predictive, Prescriptive.​

Example: Sales dropped (Descriptive) because returns increased (Diagnostic).
a

3. What is a KPI?
an

Answer: A measurable value that indicates performance.​

Example: Customer Retention %, Monthly Revenue, AOV.
Jn

4. Difference between KPI & Metric?

Answer: KPI is goal-oriented, metric is just a measurement.​

Example: Metric = Daily Orders, KPI = Order Growth %.

5. What is Data Cleaning?

Jnana Pravallika
Answer: Removing errors, duplicates, nulls and formatting issues.​
Example: Standardizing "M", "Male", "male" → "Male".

6. What is Data Transformation?

Answer: Converting raw data into usable structure or format.​

Example: Convert text date "12-05-24" → Date format.

a
7. What is Data Pipeline?

llik
Answer: End-to-end data flow from source → storage → analysis.​
Example: Orders → ETL → Snowflake → Power BI dashboard.

8. What is ETL? va
Answer: Extract → Transform → Load process for preparing data.​
a
Example: Load cleaned customer data to data warehouse.
Pr

9. Difference between ETL & ELT?

Answer: ETL transforms before loading, ELT transforms after loading.​

a

Example: Snowflake prefers ELT for large transformation workloads.

an

10. What is Data Modelling?

Jn

Answer: Structuring tables for efficient analysis & reporting.​

Example: FactSales linked with DimCustomer & DimProduct.

11. What is Fact Table?

Answer: Contains numeric transactional values.​

Example: SalesAmount, Quantity, Revenue.

Jnana Pravallika
12. What is Dimension Table?

Answer: Contains descriptive attributes.​

Example: Customer Name, City, Category.

13. What is Star Schema?

Answer: Fact table connected directly to all dimensions.​

Example: FactSales ↔ DimDate, DimProduct, DimRegion.

a
llik
14. What is Snowflake Schema?

Answer: Dimensions are normalized into sub-tables.​

Example: Product → Category → Brand hierarchy.

15. What is Dashboard?

a va
Answer: A visual summary of KPIs for decision making.​
Pr

Example: Power BI dashboard showing revenue, conversions & ROI.

16. What is Drill Down?

a

Answer: Breaking summary into detailed view.​

an

Example: Click Region → shows Cities → Stores → Orders.

Jn

17. What is Drill Through?

Answer: Navigate to dedicated detail page for specific entity.​

Example: Right-click Product → View Transaction History page.

18. What is Slicing & Dicing?

Answer: Filtering & rearranging data for deeper insights.​

Example: Analyze Sales by Region → then by Product → then by Month.

Jnana Pravallika
19. What is Exploratory Data Analysis (EDA)?

Answer: Understanding data patterns using summary & visuals.​

Example: Boxplot detects outliers in sales values.

20. What is Correlation?

Answer: Relationship strength between two variables.​

a
Example: Ads ↑ Sales ↑ = +0.85 correlation.

llik
21. Does correlation mean causation?

va
Answer: No — correlation may be coincidental.​
Example: Ice-cream sales ↑ & drowning cases ↑ (due to summer).
a
22. What is Hypothesis Testing?
Pr

Answer: Statistical test to validate assumptions.​

Example: Testing if Discount increases conversions.
a

23. What is p-value?

an

Answer: Probability of observing results when H0 is true.​

Example: p < 0.05 → Reject null → change is significant.
Jn

24. What is A/B Testing?

Answer: Compare two version outcomes to choose best.​

Example: Homepage B CTR = 6% > A CTR = 3%.

25. What is Outlier?

Jnana Pravallika
Answer: Unusually high/low value.​
Example: One order ₹1.5L when avg is ₹2000.

26. How to treat outliers?

Answer: Remove, cap, transform, analyze cause.​

Example: Cap extreme values using Winsorization.

a
27. What is Data Quality?

llik
Answer: Measures correctness, completeness, consistency.​
Example: Duplicates & nulls indicate poor data quality.

28. What is Data Validation? va

Answer: Checking accuracy & consistency before use.​
a
Example: Validate phone number = 10 digits only.
Pr

29. What is Churn Analysis?

Answer: Identifying customers likely to leave.​

a

Example: Inactive 90 days → churn risk.

an

30. How do you deliver insights?

Jn

Answer: Present key findings with visuals & action points.​

Example: “Revenue fell 12% due to high return rate in South.”

Jnana Pravallika
📌 DATA ANALYTICS — SCENARIO BASED INTERVIEW
QUESTIONS (Practical Problems)

1. Sales dropped by 15% this quarter. What will you analyze first?

Approach: Compare YoY, MoM, Region, Product, Price & Return patterns.​
Answer:​
"I will break down sales by region/product, compare MoM trend & identify
drop-driving segments."

a
llik
2. Revenue is increasing but profit margin is decreasing — explain why.

Possible Findings:​
✔ High discounting​
✔ Advertising cost increased​
✔ Supplier cost increase
a va
Pr

3. Customer acquisition increased but retention fell — what can be

wrong?

Answer:​
a

Poor onboarding, product experience issues, price sensitivity, weak engagement.

an

4. You found missing values in 20% of the dataset — what will you do?
Jn

Approach:​
Profile → Pattern check → Impute → Drop only if necessary.

5. If return rate spikes suddenly, how will you identify reason?

Approach:​
Drill returns by product, vendor, order date, region.

Jnana Pravallika
6. Two dashboards show different numbers — what will you do?

Approach:​
Validate sources, KPI definitions, calculation logic → reconcile differences.

7. Marketing budget doubled but conversions did not change — what’s

your step?

a
Answer:​

llik
Check campaign quality, targeting relevance, landing page UX, ad fatigue.

va
8. You need to build a KPI dashboard — what will you include?

KPI Set: Revenue, CAC, Repeat Orders %, AOV, Churn, Funnel Conversion.
a
Pr

9. How do you clean raw customer data?

Steps: Remove duplicates → Handle nulls → Standardize → Validate format.

a
an

10. Management wants customer churn prediction — how would you?

Approach: RFM scoring → ML model using purchase history + engagement.

Jn

11. Top SKUs account for 80% revenue — how to identify?

Pareto Insight:​
Sort by revenue → cumulative % → identify 80/20 split.

12. Website traffic high but conversions low — root cause?

Jnana Pravallika
Answer:​
Poor UX, pricing mismatch, slow checkout, trust barrier.

13. Customer complaints are rising — how to quantify impact?

Approach:​
Calculate % defect complaints vs total orders → show trend over time.

a
14. Inventory aging increased — what could be the reason?

llik
Answer:​
Demand prediction failure, overstocking, seasonal mismatch.

va
15. You discover outliers in purchase history — what to do?
a
Approach: Analyze cause → cap/remove if noise → retain if VIP users.
Pr

16. Profit rose but order volume remained same — what changed?
a

Possible Insights:​
Higher AOV, less returns, price hike, upselling success.
an

17. CAC is going up but ROAS dropping — insight?

Jn

Answer:​
Ad inefficiency, audience saturation, weak creative performance.

18. If 25% of users add to cart but only 3% checkout — what does it
mean?

Insight:​
Checkout friction → solve via UX optimization, COD options, trust badges.

Jnana Pravallika
19. Company wants to reduce delivery time — how do you measure
success?

Metric: Avg delivery time Before vs After.

20. Repeat purchase rate stagnant — what metric will you check?

a
Approach: Cohort retention curve & RFM distribution.

llik
21. Advertisement spend increases but CPA increases too — why?

Reason:​
Competition ↑, bid inflation, poor targeting.
a va
Pr

22. Two products have equal revenue, which one is better?

Factor: Compare profit margin, repeat orders, return rate.

a

23. How will you evaluate store performance difference?

an

Approach: Compare Revenue/Footfall/Conversion/Profit per store.

Jn

24. How do you handle skewed data?

Action: Log/boxcox transform or remove extreme outliers.

25. Sudden traffic spike — what analysis will you perform?

Checklist: Breakdown by channel, geography, campaign, time.

Jnana Pravallika
26. Identify top customers contributing most revenue.

Approach: RFM scoring + Pareto contribution.

27. If churn increases in one region only — next step?

Answer:​

a
Targeted survey + pricing sensitivity + regional logistics issues.

llik
28. Customer buying frequency dropped — how to improve?

Strategy:​
va
Cashbacks, subscriptions, loyalty program, personalized emails.
a
29. You found inconsistent data across months — next step?
Pr

Audit sources → data validation logs → ETL pipeline check.

a

30. Your model accuracy is low — how to improve?

an

Feature engineering → Hyperparameter tuning → Balanced dataset.

Jn

SECTION 2 — SQL (30 Most Important Questions +

Answers + Examples)

1. What is SQL?

Jnana Pravallika
Answer: Structured Query Language used to store, manipulate and retrieve data
from databases.​
Example:

SELECT * FROM employees;

2. What is a Primary Key?

Answer: Unique identifier for each row; cannot be NULL.​

a
Example: EmployeeID in Employee table.

llik
3. What is a Foreign Key?

Example:​
va
Answer: A field that links records between two tables.​

Orders(CustomerID) → references Customers(CustomerID).

a
Pr

4. Difference between WHERE & HAVING?

Answer:​
WHERE filters rows before aggregation; HAVING filters aggregated results.​
a

Example:
an

SELECT dept,COUNT(*) FROM emp GROUP BY dept HAVING COUNT(*)>10;

Jn

5. What is GROUP BY used for?

Answer: To aggregate data by categories.​

Example:

SELECT city,SUM(sales) FROM orders GROUP BY city;

Jnana Pravallika
6. What does ORDER BY do?

Answer: Sorts results ascending or descending.​

Example:

SELECT * FROM sales ORDER BY revenue DESC;

7. What are SQL JOINS?

a
Answer: Technique to retrieve data from multiple tables using related keys.​
Example:

llik
SELECT * FROM orders o
JOIN customers c ON o.customer_id=c.customer_id;

8. Types of Joins?
a va
Answer: INNER, LEFT, RIGHT, FULL, CROSS, SELF Join.​
Pr

Example use: Left Join retrieves all customers with or without orders.
a

9. Difference between INNER & LEFT JOIN?

an

Answer:​
INNER → only matching rows​
LEFT → all left side rows + matches from right​
Example:
Jn

SELECT * FROM A LEFT JOIN B ON [Link]=[Link];

10. What is a Subquery?

Answer: A query inside another query.​

Example:

SELECT name FROM emp WHERE salary>(SELECT AVG(salary) FROM emp);

Jnana Pravallika
11. What is a CTE (WITH Clause)?

Answer: Temporary result used within query for readability.​

Example:

WITH sale AS (SELECT * FROM orders WHERE amount>1000)

SELECT * FROM sale;

a
12. What are Window Functions?

llik
Answer: Functions to rank, accumulate, compare rows without collapsing.​
Example:

ROW_NUMBER() OVER (ORDER BY sales DESC)

a va
13. RANK vs DENSE_RANK vs ROW_NUMBER?
Pr

Answer:​
RANK skips numbers on ties, DENSE_RANK doesn’t, ROW_NUMBER always
unique.
a
an

14. How to find the second highest salary?

SELECT salary FROM emp ORDER BY salary DESC LIMIT 1 OFFSET 1;
Jn

Or
SELECT MAX(salary)
FROM employees
WHERE salary < (SELECT MAX(salary) FROM employees);

15. How to fetch top 3 salaries?

SELECT salary FROM emp ORDER BY salary DESC LIMIT 3;

Jnana Pravallika
16. How to count unique values?
SELECT COUNT(DISTINCT employee_id) FROM attendance;

17. What is UNION vs UNION ALL?

a
Answer:​
UNION removes duplicates; UNION ALL keeps all.​

llik
Example:

SELECT city FROM A UNION ALL SELECT city FROM B;

va
18. DELETE vs TRUNCATE vs DROP?
a
●​ DELETE removes row-wise, rollback possible.​
Pr

●​ TRUNCATE removes all rows, faster.​

●​ DROP removes entire table.​

a
an

19. What is Normalization?

Jn

Answer: Structuring tables to remove redundancy.​

Example: Storing customer details in separate table instead duplicate every record.

20. What is Denormalization?

Answer: Adding redundancy for faster reads.​

Example: Merging tables used frequently for reporting.

Jnana Pravallika
21. What is Index?

Answer: Improves query speed by fast lookup.​

Example:

CREATE INDEX idx_name ON employees(name);

a
22. When not to use Index?

llik
Answer: On small tables or frequent updates → slows write performance.

23. What is a Stored Procedure? va

Answer: Predefined collection of SQL statements saved for reuse.​
a
Example:
Pr

CREATE PROCEDURE GetSales AS SELECT * FROM sales;

a

24. What are Triggers?

an

Answer: Auto actions executed on insert/update/delete.​

Example: Audit log trigger when salary updated.
Jn

25. What is a View?

Answer: Virtual table from a query, doesn't store data physically.​

Example:

CREATE VIEW active_customers AS SELECT * FROM customers WHERE

status='active';

26. What is a Self Join?

Jnana Pravallika
Answer: Join table with itself.​
Example: Find employee's manager from same table.

27. What is NULL in SQL?

Answer: Unknown or missing value, not zero or empty.

a
28. How to replace NULL values?
SELECT COALESCE(phone,'Not Available') FROM customer;

llik
29. What is ACID property?
va
Atomicity, Consistency, Isolation, Durability — ensures reliable transactions.
a
Pr

30. Real-world SQL Scenario

Question: Sales dropped 20% — find product/category trend.​

Answer/Example:
a

SELECT category,SUM(sales) AS total

an

FROM orders
WHERE order_date BETWEEN '2024-07-01' AND '2024-07-31'
GROUP BY category
ORDER BY total ASC;
Jn

SQL SCENARIO-BASED QUESTIONS (Set 1)

1. Find the top 3 selling products by revenue.
SELECT product_id, SUM(amount) AS revenue
FROM sales
GROUP BY product_id
ORDER BY revenue DESC
LIMIT 3;

Jnana Pravallika
2. Find customers who placed orders in 2023 but not in 2024.
SELECT DISTINCT customer_id
FROM orders
WHERE YEAR(order_date)=2023
AND customer_id NOT IN (
SELECT DISTINCT customer_id FROM orders WHERE
YEAR(order_date)=2024
);

a
llik
3. Get month-wise revenue growth percentage.
SELECT
MONTH(order_date) AS month,
SUM(amount) AS revenue,
va
LAG(SUM(amount)) OVER (ORDER BY MONTH(order_date)) AS
a
prev_revenue,
Pr

((SUM(amount) - LAG(SUM(amount)) OVER (ORDER BY

MONTH(order_date)))
/ LAG(SUM(amount)) OVER (ORDER BY MONTH(order_date))) *
100 AS growth_percent
a

FROM sales
GROUP BY MONTH(order_date);
an
Jn

4. Find the second highest revenue-generating category.

SELECT category, SUM(sales) AS total
FROM products JOIN orders USING(product_id)
GROUP BY category
ORDER BY total DESC
LIMIT 1 OFFSET 1;

Jnana Pravallika
5. Find average order value (AOV) per customer.
SELECT customer_id,
SUM(amount)/COUNT(order_id) AS avg_order_value
FROM orders
GROUP BY customer_id;

6. Get customers who have purchased more than the average number of
orders.

a
WITH summary AS (

llik
SELECT customer_id, COUNT(*) AS total_orders
FROM orders GROUP BY customer_id
)
SELECT * FROM summary
va
WHERE total_orders > (SELECT AVG(total_orders) FROM summary);
a
Pr

7. Identify products ordered in every month of a year.

SELECT product_id
FROM orders
WHERE YEAR(order_date)=2024
a

GROUP BY product_id
an

HAVING COUNT(DISTINCT MONTH(order_date)) = 12;

Jn

8. Which customer generated the highest profit?

SELECT customer_id, SUM(profit) AS total_profit
FROM sales
GROUP BY customer_id
ORDER BY total_profit DESC
LIMIT 1;

Jnana Pravallika
9. Find repeat vs one-time customers.
SELECT
customer_id,
CASE WHEN COUNT(order_id)>1 THEN 'Repeat' ELSE 'One-time' END
AS type
FROM orders
GROUP BY customer_id;

a
10. Detect months where revenue dropped compared to previous month.

llik
SELECT
month,
revenue,
prev_revenue,
va
CASE WHEN revenue < prev_revenue THEN 'Drop' ELSE 'Growth' END
AS status
FROM (
a
SELECT
Pr

MONTH(order_date) AS month,
SUM(amount) AS revenue,
LAG(SUM(amount)) OVER (ORDER BY MONTH(order_date)) AS
prev_revenue
a

FROM orders
GROUP BY MONTH(order_date)
an

) t;
Jn

SQL SCENARIO-BASED QUESTIONS (Set 2 – More

Complex)
11. Find employees earning above average salary of their department.
SELECT employee_id, name, dept, salary
FROM emp e
WHERE salary > (

Jnana Pravallika
 SELECT AVG(salary) FROM emp WHERE dept = [Link]
);

12. Get top 5 revenue months for last year only.

SELECT MONTH(order_date) AS month, SUM(amount) AS revenue
FROM orders
WHERE YEAR(order_date)=2023
GROUP BY MONTH(order_date)
ORDER BY revenue DESC

a
LIMIT 5;

llik
13. Find customers who purchased only 1 product category ever.
SELECT customer_id
FROM orders
va
GROUP BY customer_id
a
HAVING COUNT(DISTINCT category)=1;
Pr

14. Find the most frequent buying weekday.

a

SELECT DAYNAME(order_date) AS weekday, COUNT(*) AS orders

an

FROM orders
GROUP BY DAYNAME(order_date)
ORDER BY orders DESC
Jn

LIMIT 1;

15. Retrieve last purchase date for each customer.

SELECT customer_id, MAX(order_date) AS last_purchase
FROM orders
GROUP BY customer_id;

Jnana Pravallika
16. Compare sales of Q1 vs Q2.
SELECT
SUM(CASE WHEN QUARTER(order_date)=1 THEN amount END) AS Q1,
SUM(CASE WHEN QUARTER(order_date)=2 THEN amount END) AS Q2
FROM orders;

a
17. Get the most returned product.

llik
SELECT product_id, COUNT(return_id) AS return_count
FROM returns
GROUP BY product_id
ORDER BY return_count DESC
LIMIT 1;
a va
Pr

18. Identify customers inactive for 60+ days.

SELECT customer_id
FROM orders o
GROUP BY customer_id
a

HAVING DATEDIFF(CURDATE(), MAX(order_date)) > 60;

an
Jn

19. Get sales contribution % of each category.

SELECT
category,
SUM(amount) AS revenue,
SUM(amount)/ (SELECT SUM(amount) FROM orders)*100 AS
contribution_percent
FROM orders
GROUP BY category;

Jnana Pravallika
20. Get top 3 customers by revenue in each region.
SELECT *
FROM (
SELECT region, customer_id, SUM(amount) AS revenue,
RANK() OVER(PARTITION BY region ORDER BY
SUM(amount) DESC) AS rnk
FROM orders
GROUP BY region, customer_id

a
) t WHERE rnk <= 3;

llik
EXCEL INTERVIEW QUESTIONS (Theory + Practical +
Scenarios)
a va
1. What is Excel used for in data analytics?
Pr

Answer: Data cleaning, transformation, analysis, reporting, dashboarding.​

Example: Pivot table for monthly revenue summary.
a

2. What is the difference between CONCATENATE & TEXTJOIN?

an

Answer: TEXTJOIN handles delimiters & ignoring blanks while CONCATENATE

does not.​
Jn

Example:

=TEXTJOIN(", ",TRUE,A2:A6)

3. What is VLOOKUP?

Answer: Used to find a value in the first column and return data from another
column.​
Example:

Jnana Pravallika
=VLOOKUP(A2,Sheet2!A:E,4,FALSE)

4. Why is XLOOKUP better than VLOOKUP?

Answer: Supports left lookup, multi-column return, error handling.​

Example:

=XLOOKUP(A2,Product_ID,Price)

a
llik
5. Difference between VLOOKUP and INDEX-MATCH?

Answer: INDEX-MATCH is flexible, faster, supports left lookup.

a va
6. When do you use Pivot Table?

Answer: When analyzing & summarizing large datasets.​

Pr

Example: Region-wise total sales with drilldown.

a

7. What are slicers?

an

Answer: Visual filters used in PivotTable & dashboards.

Jn

8. What is Data Validation?

Answer: Restrict user input to valid values.​

Example: Only allow Yes/No using dropdown.

9. How do you remove duplicates in Excel?

Answer:​
Data → Remove Duplicates

Jnana Pravallika
10. What is Power Query?

Answer: Excel/Power BI tool for ETL data preparation.​

Example: Merge two tables → reshape → load to Excel.

11. What is the difference between Merge & Append in Power Query?

a
Answer:

llik
●​ Merge = JOIN​

●​ Append = UNION (Stack data)​

a va
12. What is Group By function in Power Query?
Pr

Answer: Summarizes & aggregates data inside query.​

Example: Sales by category.
a

13. How to handle missing/blank values?

an

Answer: Replace with mean/median/manual input; or remove.

Jn

14. What is Conditional Formatting?

Answer: Highlight rows based on values.​

Example: Highlight sales < 10,000 in red.

15. How to find duplicate entries?

Jnana Pravallika
Answer:​
Conditional Formatting → Duplicate Values

16. How do you create a dashboard in Excel?

Answer:​
Use pivot tables + pivot charts + slicers + KPI cards.

a
17. What is Power Pivot?

llik
Answer: Data modelling tool inside Excel to handle large datasets using DAX.

18. What is a Pivot Chart? va

Answer: Chart built directly from PivotTable.
a
Pr

19. What is Goal Seek?

Answer: Reverse calculation to achieve desired result.​

a

Example: Find price needed to reach ₹50k revenue.

an

20. What is What-If Analysis?

Jn

Answer: Scenario-based change outcome projection.​

Example: If discount = 10%, profit change = ?

21. What are Named Ranges?

Answer: Assign readable name to a cell range.​

Example: Products = A2:A100

Jnana Pravallika
22. How to automate data refresh?

Answer: Power Query Refresh / VBA script.

23. How to calculate Running Total?

Answer:

=SUM($B$2:B2)

a
llik
24. How do you detect outliers using Excel?

Answer: Using boxplot, IQR rule & conditional highlight.

a va
25. What does IFERROR do?
Pr

Answer: Catches formula errors & returns alternate output.

=IFERROR(VLOOKUP(A2,B:E,3,FALSE), "Not Found")

a
an

26. Explain SUBSTITUTE function.

Answer: Replace specific text in a string.

Jn

=SUBSTITUTE(A2,"_"," ")

27. Explain LEFT, RIGHT, MID functions.

Answer: Extract text portions.

=LEFT(Name,3)
=RIGHT(Code,2)

Jnana Pravallika
=MID(Text,Start,Length)

28. Difference between COUNT, COUNTA & COUNTIF?

Answer:

●​ COUNT = numerical cells​

●​ COUNTA = non-empty​

a
●​ COUNTIF = count based on condition​

llik
va
29. How do you merge datasets with different structure?

Answer:​
a
Power Query → Merge via common key​
Pr

OR INDEX-MATCH for manual lookup.

30. How to convert rows into columns?

a

Answer: Power Query PIVOT feature.

an

SCENARIO-BASED EXCEL QUESTIONS

Jn

Scenario 1:

You have Sales Data — find which region is performing worst.

Solution:​
Create Pivot Table → Region in Rows → Sum of Sales → Sort Ascending.

Jnana Pravallika
Scenario 2:

Manager wants a dashboard of monthly revenue growth.

Solution:

●​ Create Month column using =TEXT(Date,"MMM")​

●​ Build Pivot Chart → Line → Add Slicer​

●​ Add YoY / MoM KPI indicators in dashboard​

a
llik
Scenario 3:

va
You need to combine 12 monthly files into one sheet automatically.

Solution:​
Use Power Query → Folder Import → Append → Refresh monthly.
a
Pr

Scenario 4:

CEO wants customer churn summary.

a

Solution:​
an

Flag inactive customers (>90 days last order) using formula:

=IF(TODAY()-MAX(PurchaseDate)>90, "Churn", "Active")

Jn

Scenario 5:

Highlight product sales below target ₹50,000.

Solution:​
Conditional Formatting → Rule →

= B2 < 50000

Jnana Pravallika
SECTION 4 — POWER BI (30 Interview Questions +
Answers + Real Scenarios)

1. What is Power BI?

Answer: A Business Intelligence tool used for data modeling, visualization, reporting
& analytics.​
Example: Build sales dashboard with KPIs, region trends, category insights.

a
llik
2. What is Power Query?

Answer: ETL data preparation engine inside Power BI for cleaning & transformation.​
Example: Remove duplicates → merge → fill blanks → load to model.

3. What is DAX?
a va
Answer: Data Analysis Expressions — a formula language for calculations in Power
Pr

BI.

4. What is data modeling in Power BI?

a

Answer: Designing relationships between tables (fact & dimension) for optimized
an

reporting.
Jn

5. Difference between Fact & Dimension tables

Answer:​
Fact = numeric metrics​
Dimension = descriptive attributes​
Example: FactSales + DimProduct + DimDate.

6. What is Star Schema?

Answer: Fact table in center linked to all dimensions — best modeling structure.

Jnana Pravallika
7. What is Snowflake Schema?

Answer: Dimensions further normalized into sub tables — reduces redundancy but
adds joins.

8. What are Measures in Power BI?

Answer: Dynamic calculations that change based on filter context.​

a
Example:

llik
Total Sales = SUM(Sales[Amount])

9. What is a Calculated Column?

va
Answer: A static computed field stored in table.​
Example: Profit = Sales - Cost.
a
Pr

10. Difference between Measures & Calculated Columns?

Answer:​
Measure = dynamic​
a

Column = stored & static​

Usage Example: YoY growth = Measure.
an

11. What is CALCULATE() in DAX?

Jn

Answer: Changes/overrides filter context of a calculation.​

Example:

Last Year Sales = CALCULATE([Total Sales],

SAMEPERIODLASTYEAR(Date[Date]))

12. What is Row-Level Security (RLS)?

Jnana Pravallika
Answer: Restricts data visibility based on user/role.​
Example: Sales rep sees only their region.

13. What are Bookmarks?

Answer: Saved report states used for page navigation, toggles & storytelling.

14. What are Slicers used for?

a
Answer: Dashboard filters for user-interaction.​

llik
Example: Filter sales by Region, Category, Date.

15. What is Drill-Through?

va
Answer: Go from summary page → detailed page for a specific item.​
Example: Click product → open transaction history page.
a
Pr

16. Explain Drill-Down

Answer: View data hierarchy levels progressively.​

Example: Year → Quarter → Month → Day.
a
an

17. What is a KPI Visual?

Answer: Shows achievement vs target with indicators.​

Jn

Example: Sales Target = 12Cr → Achieved 10Cr (83%).

18. What is a Tooltip page?

Answer: Pop-up detail panel on hover.​

Example: Hover product bar → show MoM, YoY, avg price.

19. What are Field Parameters?

Jnana Pravallika
Answer: Allows switching between metrics dynamically.​
Example: Toggle between Sales/Profit/AOV in same chart.

20. What is Data Refresh?

Answer: Automated schedule to update reports from connected source.

21. Difference between Import mode and DirectQuery?

a
Answer:​

llik
Import = faster, cached data​
DirectQuery = live DB connection, slower visual loads

22. What are Dataflows? va

Answer: Cloud-based Power Query pipelines for shared ETL logic.
a
Pr

23. What is Q&A Visual?

Answer: Natural language-based insights generator.​

Example: Type "Top 5 states by sales" → chart appears.
a
an

24. What is a Composite Model?

Answer: Uses both Import + DirectQuery in same dataset.

Jn

25. What is Aggregation Table?

Answer: Summary table to boost performance by reducing row-level processing.

26. What causes slow report performance?

Jnana Pravallika
Answer:

Slow performance in Power BI usually occurs due to:

●​ Large or unoptimized data models​

●​ High-cardinality columns (unique text values, long strings)​

●​ Too many visuals and interactions on a page​

●​ Complex or non-optimized DAX calculations​

a
●​ Non-star schema / improper data modeling​

llik
●​ Using DirectQuery instead of Import for heavy sources​

●​ Lack of aggregation tables​

va
●​ Auto date/time enabled for every date column​

●​ Unnecessary columns & tables included in the model​

a
Pr

Short Answer:​
Poor modeling, high cardinality, heavy DAX, too many visuals & large datasets
are the main reasons for slow performance.
a

27. How to improve performance?

an

Answer:

You improve Power BI performance by optimizing data model, queries, visuals &
Jn

DAX. Key techniques:

🔹 Data Modeling Optimization

●​ Use Star Schema​

●​ Remove unused columns/tables​

●​ Reduce cardinality (avoid unique text fields)​

●​ Use summary tables or aggregations​

Jnana Pravallika
🔹 Power Query Optimization
●​ Enable Query Folding​

●​ Clean & filter data at source​

●​ Use Incremental Refresh for big data​

🔹 DAX Optimization
●​ Prefer simple columnar measures over heavy iterators (SUMX, FILTER)​

a
●​ Use VAR to reduce repeated computations​

llik
●​ Pre-calculate logic in Power Query where possible​

🔹 Visualization Optimization va
●​ Reduce number of visuals per report page​
a
●​ Avoid high-custom visuals if not needed​
Pr

●​ Use optimized slicers, tooltips & interactions​

Short Answer:​
a

Improve performance using star schema, query folding, column reduction,

optimized DAX and fewer visuals.
an

28. What is Query Folding in Power Query?

Jn

Answer: Push transformation logic back to database for faster execution.

29. What are Custom Visuals?

Answer: Additional charts installed from marketplace.​

Example: Sankey, Decomposition tree, Bullet chart.

Jnana Pravallika
30. Explain Time Intelligence in DAX

Answer: Functions to calculate date-based metrics (YoY, MoM, YTD).​

Example:

YoY Growth % = ([Sales] - [Last Year Sales])/[Last Year Sales]

POWER BI SCENARIO-BASED QUESTIONS (HIGHLY

ASKED)

a
llik
Scenario 1

🔹 "Sales dropped this month — how will you analyze in Power BI?"​
Answer:​
✔ Compare YoY/MoM using date intelligence​
✔ Drilldown region → category → product​
a va
✔ Check return rate, out-of-stock impact​
✔ Highlight KPI variance using conditional formatting
Pr

Scenario 2

🔹 "CEO wants only top KPIs in one page — what will you include?"​
a
an

Answer: Revenue, Profit %, AOV, Conversion Rate, YoY Trend, Top 5 Products,
Region Map.
Jn

Scenario 3

🔹 "Dashboard taking too long to refresh — solutions?"​

Answer:​
✔ Reduce model size​
✔ Remove unnecessary columns​
✔ Disable Auto Date/Time​
✔ Use Star Schema​
✔ Use Aggregations table

Jnana Pravallika
Scenario 4

🔹 "Need report where user can switch between Sales/Profit/Quantity."​

Solution: Field Parameters or Calculation Groups.

Scenario 5

🔹 "Show regional manager-wise access only."​

Solution: Implement Row-Level Security (RLS) using username() filter.

a
llik
SECTION 5 — PYTHON for DATA ANALYTICS
30 Most Important Questions + Answers + Examples + Real Scenarios

va
1. What is Python used for in data analytics?
a
Answer: Data cleaning, EDA, visualization, automation & model building.​
Pr

Example: Clean sales dataset using pandas & build visual charts using matplotlib.
a

2. What are Pandas in Python?

an

Answer: A library for manipulating, cleaning & analyzing tabular data.​

Example:

import pandas as pd
Jn

df = pd.read_csv("[Link]")

3. How do you display first few rows?

[Link]()

Jnana Pravallika
4. How to check missing values?
[Link]().sum()

5. How to drop missing values?

[Link](inplace=True)

a
6. How to fill missing values?
df['Age'].fillna(df['Age'].median(), inplace=True)

llik
7. How to merge two datasets?
df3 = [Link](df1, df2, on='customer_id')
a va
Pr

8. Difference between merge() and concat()?

Answer: Merge joins tables on key, concat stacks data vertically/horizontally.

a
an

9. How to filter data?

df[df['Sales'] > 5000]
Jn

10. How to group data & aggregate?

[Link]('Region')['Sales'].sum()

11. How to sort values?

Jnana Pravallika
df.sort_values('Sales', ascending=False)

12. How to remove duplicates?

df.drop_duplicates(inplace=True)

a
13. How to convert datatype?
df['Date'] = pd.to_datetime(df['Date'])

llik
14. What is lambda function?

Answer: Single-line anonymous function.​

va
Example:
a
df['Tax'] = df['Sales'].apply(lambda x: x * 0.18)
Pr
a

15. How to create new column?

df['Profit'] = df['Sales'] - df['Cost']
an
Jn

16. What is One-Hot Encoding?

pd.get_dummies(df['Category'])

17. What is Label Encoding?

from [Link] import LabelEncoder
encoder = LabelEncoder()
df['City'] = encoder.fit_transform(df['City'])

Jnana Pravallika
18. How to detect outliers using IQR?
Q1 = df['Sales'].quantile(0.25)
Q3 = df['Sales'].quantile(0.75)
IQR = Q3 - Q1
df[df['Sales'] > Q3 + 1.5*IQR]

a
llik
19. What is EDA?

Answer: Exploring data using statistics & visualization for pattern discovery.

20. Which libraries used for visualization?

a va
Answer: Matplotlib, Seaborn, Plotly.
Pr

21. Plot line chart in python

a

import [Link] as plt

[Link](df['Month'], df['Sales'])
an

[Link]()
Jn

22. Distribution plot

import seaborn as sns
[Link](df['Profit'])

23. Correlation Heatmap

[Link]([Link](), annot=True)

Jnana Pravallika
24. How to export dataframe to Excel?
df.to_excel("[Link]", index=False)

25. Read SQL data into Python

a
import sqlalchemy
pd.read_sql("SELECT * FROM Orders", engine)

llik
26. Automation script example
import schedule, time
def refresh():
a va
df = pd.read_csv("[Link]")
[Link]().[Link](refresh)
Pr
a

27. How to handle large datasets?

an

Answer: Use chunksize, Dask, DuckDB, vectorized operations.

Jn

28. JSON to DataFrame

df = pd.read_json("[Link]")

29. Remove whitespaces

df['Name'] = df['Name'].[Link]()

Jnana Pravallika
30. Convert text to lowercase
df['City'] = df['City'].[Link]()

PYTHON SCENARIO-BASED QUESTIONS

a
llik
Scenario 1

Extract customers whose last purchase was more than 90 days ago.

va
inactive = df[df['Last_Purchase_Days'] > 90]
a
Scenario 2
Pr

Find top 5 highest revenue-generating cities.

[Link]('City')['Revenue'].sum().sort_values(ascending=Fals
e).head(5)
a
an

Scenario 3
Jn

Identify products contributing 80% of sales (Pareto).

df_sales =
[Link]('Product')['Sales'].sum().sort_values(ascending=Fal
se)
df_sales[df_sales.cumsum()/df_sales.sum() <= 0.8]

Jnana Pravallika
Scenario 4

Calculate YoY growth.

df['YoY Growth %'] = ((df['Sales'] - df['Sales_last_year']) /

df['Sales_last_year']) * 100

Scenario 5

a
Create automated sales summary dashboard output.

llik
summary = [Link]('Month')['Sales'].sum()
[Link](kind='bar')
a va
SECTION 6 — STATISTICS for DATA ANALYTICS
Pr

30 Interview Questions + Answers + Real Examples + Scenarios

a

1. What is Statistics in Data Analysis?

an

Answer: Science of collecting, analyzing, interpreting and presenting data.​

Example: Analyzing customer behaviour and predicting churn.
Jn

2. What are the two types of Statistics?

Answer:

1.​ Descriptive — summarizing data​

2.​Inferential — drawing conclusions from sample to population​

Jnana Pravallika
3. What is Mean, Median & Mode?

Answer:​
Mean = Average​
Median = Middle value​
Mode = Most frequent​
Example: [2,2,5,8] → Mean=4.25, Median=3.5, Mode=2

a
4. What is Standard Deviation?

llik
Answer: Measures spread of data from mean.​
Low SD ⇒ data close to mean, High SD ⇒ scattered data.

5. What is Variance?
a va
Answer: Square of standard deviation — spread measurement.​
Example: If salaries vary highly, variance will be high.
Pr

6. What is Normal Distribution?

a

Answer: Bell-shaped symmetric curve where mean=median=mode.​

an

Example: Height of population.

Jn

7. What is Skewness?

Answer: Measure of asymmetry in distribution.​

Right skew=Positive, Left skew=Negative.

8. What is Correlation?

Answer: Strength of relationship between two variables (-1 to +1).​

Example: Ads ↑ Sales ↑ → correlation 0.85.

Jnana Pravallika
9. Does Correlation imply Causation?

Answer: No — variables can move together without cause-effect relation.

10. What is Regression?

Answer: Predict outcome using input variables.​

a
Example: Predict Sales from Ad-spend, Price, Season.

llik
11. Difference between Correlation & Regression?

Answer:​
va
Correlation measures relationship, regression predicts one variable using another.
a
12. What is Hypothesis Testing?
Pr

Answer: Method to test assumptions with sample data.

a

13. What are Null & Alternative Hypotheses?

an

Answer:​
H0 = No effect/relationship​
H1 = Effect exists
Jn

14. What is p-value?

Answer: Probability of observing results assuming H0 is true.​

If p < 0.05 → Reject H0 → Result significant.

15. What is Confidence Interval?

Jnana Pravallika
Answer: Range within population parameter likely lies.​
Example: Mean height 170 cm ± 3 cm (95% CI).

16. What is Central Limit Theorem?

Answer: Sample mean approaches normal distribution as sample size increases.

a
17. What are Type 1 & Type 2 errors?

llik
Answer:​
Type 1 = False Positive (Reject True H0)​
Type 2 = False Negative (Accept False H0)

18. What is t-test?

a va
Answer: Compares means of two groups.
Pr

Independent Samples t-test → compare means of two different groups

Paired t-test → same group before/after

Example:​
a

Test whether discount improves average sales.

an

19. What is ANOVA?

Jn

Answer: Compare means of 3+ groups.​

Example: Compare sales for 3 different marketing campaigns.

20. What is Chi-Square Test?

Answer: Checks relationship between two categorical variables.​

Example: Gender vs Purchase Preference.

Jnana Pravallika
21. What is Probability?

Answer: Likelihood of an event occurring (0 to 1).

22. What is Sampling?

Answer: Selecting a subset of population for analysis.

a
23. What is Population vs Sample?

llik
Answer:​
Population = Entire data group​
Sample = Small portion selected for analysis

24. What is Outlier?

a va
Answer: Unusually extreme value.​
Pr

Example: Salary ₹45 Lakhs in a dataset of avg ₹6 Lakhs.

a

25. How to detect outliers?

an

Answer: Boxplot, Z-score, IQR, Scatter plot.

Jn

26. What is Z-score?

Answer: Number of standard deviations away from mean.​

|z| > 3 ⇒ outlier.

27. What is IQR?

Answer: Inter Quartile Range = Q3 - Q1​

IQR Rule ⇒ Outliers if > Q3+1.5IQR or < Q1-1.5IQR

Jnana Pravallika
28. What is Overfitting?

Answer: Model performs well on training but poorly on new data.

29. What is Underfitting?

Answer: Model is too simple, fails to learn patterns.

a
llik
30. What is A/B Testing statistically?

Answer: Controlled experiment comparing two versions to test performance

difference using hypothesis testing.
a va
Pr

REAL STATISTICS SCENARIO QUESTIONS

Scenario 1
a

Sales dropped — how do you statistically validate the reason?​

Answer:​
an

Use hypothesis testing (t-test/Mann Whitney) to compare before & after metrics.
Jn

Scenario 2

Retention improved from 45% → 55%; is it significant?​

Answer:​
Perform proportion z-test → check p-value < 0.05.

Scenario 3

Jnana Pravallika
Which ad campaign performed best among 3?​
Answer:​
Use ANOVA to compare campaign mean conversions.

Scenario 4

Predict impact of discount on revenue.​

Answer:​
Run regression model Revenue ~ Discount%.

a
llik
Scenario 5

Is purchase preference related to gender?​

Answer:​
Use Chi-square test of independence.
a va
SECTION 7 — BUSINESS CASE STUDIES / SCENARIO
Pr

QUESTIONS (50 Real-World Answers Included)

These are the same type of questions startups, MNCs & product companies ask in
a

final rounds.
an

BUSINESS ANALYTICS CASE QUESTIONS (Set 1)

Jn

1. Sales dropped 18% this quarter — what will you analyse first?

Approach:​
✔ Compare QoQ / MoM trends​
✔ Drill down by Region → Category → SKU​
✔ Identify changes in pricing, inventory, returns

Sample Answer:​
"I will segment sales drop by region/product and find root cause — returns
increased 11% last quarter."

Jnana Pravallika
2. Return rate increased — how do you analyze?

Approach:​
Check defective products, delivery delay, repeated return users.

Example Finding:​
60% returns from "Mobile Accessories" category → poor quality vendor.

a
3. You are given a dataset with missing values — what do you do?

llik
Answer:​
Profile → Identify patterns → Drop/Impute based on business impact.

Possible Insights:​
a va
4. Marketing spend doubled but revenue didn't increase — explain why?

Campaign audience irrelevant, creative ineffective, wrong channel selection.

Pr

5. Product A has high traffic but low conversion — what does it

indicate?
a

Answer:​
Poor pricing, UX issues, long checkout, missing reviews.
an

6. Identify top revenue-driving products.

Jn

Approach:​
Group sales by product → Sort descending → Top 20% give 80% revenue (Pareto).

7. How to detect customer churn?

Answer:​
No purchase in last X days, low engagement score, complaints increase.

Jnana Pravallika
8. Predict customer lifetime value (CLV)

Approach:​
Historical spend × retention duration × buying frequency.

9. Customer growth is high, but revenue stagnant — why?

Possible Reasons:​
New users low purchase frequency, high discounts, low AOV.

a
llik
10. How do you recommend pricing strategy?

Answer:​
Competitive comparison → elasticity analysis → AB testing → pricing tiers.
a va
E-COMMERCE SCENARIOS (Set 2)
Pr

11. Best-selling month in last 2 years?

a

SELECT MONTH(order_date), SUM(revenue)

an

FROM orders GROUP BY MONTH(order_date)

ORDER BY SUM(revenue) DESC LIMIT 1;

Jn

12. Category contributing highest returns?

SELECT category, COUNT(return_id)

FROM returns GROUP BY category ORDER BY 2 DESC;

Jnana Pravallika
13. Identify loyal customers.

Approach: RFM scoring → Recency + Frequency + Monetary.

14. Find customers who buy only during discount.

Approach:

a
SELECT customer_id FROM sales WHERE discount>0

llik
GROUP BY customer_id HAVING COUNT(*)=COUNT(CASE WHEN
discount>0 THEN 1 END);

15. Which region is losing margin?

a va
Visualization Approach:​
Pr

Region in axis → Profit% column → conditional format red.

a

FINANCE / BANKING SCENARIOS (Set 3)

an

16. Fraud detection indicators?

Jn

✔ Abnormal spending​
✔ Different geolocation​
✔ Multiple failed logins

17. Credit risk analysis — how?

Approach:​
Analyze payment history, income, overdue loans, credit score.

Jnana Pravallika
18. Customer loan default prediction — model approach?

Logistic Regression / Random Forest using 30+ borrower features.

19. Identify ATM with highest transaction failure rate.

SELECT atm_id, COUNT(*) AS failures

a
FROM logs WHERE status='failed'

llik
GROUP BY atm_id ORDER BY failures DESC LIMIT 1;

va
20. Decline in net banking usage — reason?
a
✔ Better UPI adoption​
✔ Tech issues​
Pr

✔ Failed login UX​

✔ Poor mobile app UI
a
an

RETAIL / SALES SCENARIOS (Set 4)

Jn

21. Stock-out rate increased — what will you check?

✔ Supplier delays​
✔ Forecast mismatch​
✔ Warehouse inefficiency

22. Most profitable store?

SELECT store_id, SUM(profit) FROM sales

Jnana Pravallika
GROUP BY store_id ORDER BY 2 DESC LIMIT 1;

23. Seasonal trend analysis

Approach:​
Time Series → Decompose trend + seasonality.

a
24. Low footfall but high revenue — insight?

llik
Answer: premium store with high ticket orders.

va
25. What would you track weekly for retail dashboard?

Revenue, AOV, Footfall, Conversion, Return %, Inventory Age.

a
Pr

CUSTOMER ANALYTICS SCENARIOS (Set 5)

a
an

26. How to segment customers?

RFM, Clustering, Recency-based buckets.

Jn

27. Identify customers likely to cancel subscription.

✔ Usage drop​
✔ Ticket complaints​
✔ Payment decline history

28. Low app engagement — what metrics to check?

DAU, MAU, retention curves, time spent, session frequency.

Jnana Pravallika
29. Improve customer retention — strategy?

Rewards, push notifications, referral credit, personalization.

30. Churn prediction model approach?

Train ML model with features: age, city, spend, complaints, inactivity.

a
llik
PRODUCT / SAAS SCENARIOS (Set 6)

31. Feature usage declining — what to do?

va
Collect heatmaps → survey users → remove friction → tutorial prompts.
a
Pr

32. Subscription revenue reduced — why?

Discount-heavy new users, churn > acquisition, free upgrade misuse.

a
an

33. Improve onboarding for new users

Guided tours, interactive tutorials, welcome emails, first-use rewards.

Jn

34. Dashboard usage low — how to fix?

Reduce clutter, add insights not charts, KPI highlights, bookmarks.

35. Best metric to track product stickiness?

DAU/MAU Ratio — higher = more loyal users.

Jnana Pravallika
ADVANCED — EXECUTIVE LEVEL SCENARIOS (Set 7)

36. CEO asks: "Why revenue dropped?" — respond like analyst

Breakdown:​
✔ Region​

a
✔ Category​
✔ SKU​

llik
✔ Pricing​
✔ Returns​
✔ Competition

End with Actionable Recommendation.

a va
37. If marketing ask for 30% more budget — justify or reject?
Pr

Evaluate CAC, ROI, Cohort LTV — if negative ROI → recommend optimization

instead.
a

38. Best metric to measure product growth?

an

Active Users + YoY retention + Revenue expansion.

Jn

39. If two dashboards conflict — what do you do?

Data audit → validate sources → check calc logic → align KPI definitions.

40. What makes a dashboard actionable?

Simple, visual, drillable, KPI-linked, decision-focused.

Jnana Pravallika
FINAL ROUND — REAL-LIFE QUESTIONS (Set 8)

41. Tell me one insight you found that created business impact.

Example Response:​
"I segmented users by city & found tier-2 users had higher repeat rate → company
focused ads → +18% conversion."

a
42. What will you do if your model accuracy is low?

llik
Feature selection → balanced sampling → tuning → algorithm switch.

43. How will you measure campaign success?

va
CTR → CVR → CAC → Revenue Lift → Profit ROI.
a
Pr

44. Forecast next quarter sales — method?

Time-series ARIMA/Prophet with seasonality factor.

a

45. One dashboard every analytics team must have?

an

Revenue + CAC + Retention + Cohorts + Funnel + Profit Trend.

Jn

46. Stakeholder disagrees with data result — response?

Use clear visuals, explain method, share sample proof, stay factual.

47. If deadline tight — how do you deliver?

Prioritize must-have KPIs → incremental delivery → automate tasks.

Jnana Pravallika
48. Your biggest strength as analyst?

Insight-thinking > reporting, decision-driven storytelling.

49. If given messy data — what’s your first step?

Profiling → missing values → duplicates → datatype correction.

a
50. Why should we hire you as a Data Analyst?

llik
Strong SQL, problem-solving mindset, business thinking, dashboard skills,
hypothesis-driven insights.

a va
SECTION 8 — HR & MANAGERIAL INTERVIEW
QUESTIONS (30 Q&A)
Pr

(You can use or modify these as your personal responses)

a

1. Tell me about yourself.

an

Answer:​
Start with background → skills → tools → achievements → goals.​
Example:
Jn

I am a Data Analyst skilled in SQL, Excel, Power BI, Python and

problem-solving.​
I have worked on dashboards, forecasting and insights generation
projects, and I love solving business problems using data.

2. Why do you want to be a Data Analyst?

Answer:

Jnana Pravallika
 I enjoy working with data, patterns and insights that influence
decision-making.​
Analytics gives me the ability to convert raw information into business
value.

3. Why should we hire you?

Answer:

a
I bring analytical thinking + technical skills + business mindset.​
I don’t just report data — I find insights that drive action.

llik
4. Your Strengths?

Answer Examples:​
✔ Analytical mindset​
✔ Fast learner​
a va
✔ Structured approach to problem solving​
✔ Strong SQL/Power BI skill
Pr

5. Your Weakness?
a

Answer (Smart):
an

Sometimes I get too detail-focused,​

but now I actively prioritize work based on business impact.
Jn

6. Describe a difficult problem you solved.

Answer Example:

Sales were dropping monthly — I analyzed region, category & returns,

found vendor defect issue,​
business fixed supplier → sales recovered +8%.

Jnana Pravallika
7. What motivates you?

Answer:

Solving complex problems, seeing business decisions supported by my

work.

8. Tell me a time you failed.

Answer:

a
I once overestimated delivery time for a report.​

llik
I learned better time-planning and communication.

Example Answer:
a va
9. Tell me about a successful project you handled.

I developed a Power BI dashboard that reduced reporting time by 50%

and improved visibility for management.
Pr

10. How do you handle pressure or tight deadlines?

a

Answer:
an

Break tasks → prioritize critical work → communicate clearly → deliver

iteratively.
Jn

11. If you are stuck, what do you do?

Answer:

I try alternative approaches, research solutions, check documentation,

and if needed — collaborate with teammates.

Jnana Pravallika
12. How do you handle messy/incomplete data?

Answer:

I profile, clean, validate and document assumptions before analysis.

13. Tell me about a time you managed multiple tasks.

Example:

a
I prioritized weekly sales reporting + ad-hoc requests using planning &
task scheduling.

llik
14. What’s the first thing you do after receiving a project?

Answer:
va
Understand requirement → define KPIs → identify dataset.
a
Pr

15. How do you work with non-technical stakeholders?

Answer:
a

I communicate insights in simple terms — visually with charts, not

an

technical jargon.
Jn

16. Manager disagrees with your insight — response?

Answer:

Stay data-driven → support with evidence → open to feedback &

alternative view.

17. How do you decide which KPI is important?

Answer:

Jnana Pravallika
 KPI must align to business goal → measurable → actionable.

18. If business wants higher sales — what metrics you check?

Answer: Revenue trend, conversion rate, CAC, retention, return %, AOV.

19. What is your biggest professional achievement?

a
Example Answer:

llik
Built automated dashboard reducing weekly manual reporting time by 6
hours.

20. How do you validate data accuracy?

a va
Answer:
Pr

Recompute totals, cross-verify with raw source, spot-check anomalies.

21. Give an example of data-driven business decision.

a

Answer:
an

After analyzing churn, we built loyalty discount for inactive users → 20%
returned.
Jn

22. What tools are you most comfortable with?

Answer:​
SQL, Power BI/Tableau, Excel, Python (Pandas/EDA).

23. Where do you see yourself in 2–5 years?

Jnana Pravallika
Answer:

Senior Data Analyst / Data Scientist leading analytics initiatives.

24. What type of work environment suits you?

Answer:

Collaborative + analytical + growth oriented.

a
llik
25. If given 100 GB of raw data — how will you handle it?

Answer:

visualize.
a va
Process using Power Query/Dataflows/Python chunking → summarize →
Pr

26. What do you do if data doesn’t support stakeholder assumptions?

Answer:

Present evidence professionally — suggest alternate insights.

a
an

27. How do you ensure storytelling from data?

Answer:
Jn

Use dashboards, insights narrative, visuals, key takeaways & action

points.

28. Describe your ideal Data Analytics workflow.

Answer:​
Requirement → data extraction → cleaning → EDA → summary → visualization →
insights.

Jnana Pravallika
29. How do you keep improving your skills?

Answer:

Learning new tools, real datasets, online communities, case studies.

30. Why Data Analytics instead of Software Development?

a
Answer:

llik
I enjoy decision-making insights more than coding alone — analytics
connects business + logic + storytelling.
a va
Pr
a
an
Jn

Jnana Pravallika